def script():
filename = sys.argv[1]
min_sup = sys.argv[2]
D = graph_reader.graph_reader(filename)
gspan.gSpan([], D, int(min_sup))
print "Total number of patterns: {}".format(gspan.num_call - 1)
def main():
if len(sys.argv) == 1 or '-h' in sys.argv:
usage()
exit()
if '-t' in sys.argv:
opt_dict = parse_args('-n 2 -s 2 -l 2 -u 3 -v'.split(), default_args)
else:
opt_dict = parse_args(sys.argv[1:], default_args)
if not os.path.exists(opt_dict['database_file_name']):
print('{} does not exist.'.format(opt_dict['database_file_name']))
exit()
gs = gSpan(database_file_name=opt_dict['database_file_name'],
min_support=opt_dict['-s'],
min_num_vertices=opt_dict['-l'],
max_num_vertices=opt_dict['-u'],
max_ngraphs=opt_dict['-n'],
is_undirected=(opt_dict['-d'] == 0),
verbose=(opt_dict['-v'] == 1),
visualize=(opt_dict['-p'] == 1),
where=(opt_dict['-w'] == 1))
gs.run()
gs.time_stats()
def test_compound_min_graph_size_2_support_10_percent(self):
graph_dataset_size = 422
file_name = "../graphdata/benchmark_tests/Coumpound_422.txt"
supp = graph_dataset_size * 0.1
min_size_graph = 2
gs = gSpan(database_file_name=file_name,
min_support=supp,
min_num_vertices=min_size_graph)
gs.run()
gs.time_stats()
def test_chemical_min_graph_size_32_support_5_percent(self):
graph_dataset_size = 340
file_name = "../graphdata/benchmark_tests/Chemical_340.txt"
supp = graph_dataset_size * 0.05
min_size_graph = 32
gs = gSpan(database_file_name=file_name,
min_support=supp,
min_num_vertices=min_size_graph)
gs.run()
gs.time_stats()
def main(FLAGS=None):
"""Run gSpan."""
if FLAGS is None:
FLAGS, _ = parser.parse_known_args(args=sys.argv[1:])
if not os.path.exists(FLAGS.database_file_name):
print('{} does not exist.'.format(FLAGS.database_file_name))
sys.exit()
gs = gSpan(database_file_name=FLAGS.database_file_name, min_support=FLAGS.min_support)
gs.run()
gs.time_stats()
return gs
def main(args):
gs = gSpan(database_file_name=args['database_file_name'],
min_support=args['-s'],
min_num_vertices=args['-l'],
max_num_vertices=args['-u'],
max_ngraphs=args['-n'],
is_undirected=(args['-d'] == 0),
verbose=(args['-v'] == 1),
visualize=(args['-p'] == 1),
where=(args['-w'] == 1))
gs.run()
gs.time_stats()
def run_ncg(file_name, supp, min_size_graph, graphs_to_keep):
from gspan import gSpan
gs = gSpan(database_file_name=file_name,
min_support=supp,
min_num_vertices=min_size_graph,
graphs_to_keep=graphs_to_keep)
gs.run()
max_subgraphs = gs._max_subgraphs
if max_subgraphs is None:
results = []
else:
results = get_multiple_results(gs, max_subgraphs)
return results, gs
def test_chemical_min_graph_size_2(self):
graph_dataset_size = 340
file_name = "../graphdata/benchmark_tests/Chemical_340.txt"
supp = graph_dataset_size * 0.45
min_size_graph = 2
gs = gSpan(database_file_name=file_name,
min_support=supp,
min_num_vertices=min_size_graph)
gs.run()
gs.time_stats()
max_subgraphs = gs._max_subgraphs
results = self.get_multiple_results(gs, max_subgraphs)
self.updateOutput(results)
def test_testcase_00(self):
gs = gSpan(
database_file_name="../graphdata/graph.data.testcase.0",
min_support=2
)
gs.run()
max_subgraphs = gs._max_subgraphs
results = self.get_single_result(gs,max_subgraphs)
solution_1 = ('2', 'v 0 A v 1 B v 2 C v 3 D e 0 1 x e 1 2 y e 1 3 z ', '4')
solutions = [solution_1]
self.updateOutput(results)
self.assertEqual(sorted(solutions), sorted(results))
def test_testcase_11(self):
gs = gSpan(
database_file_name="../graphdata/graph.data.testcase.11",
min_support=2
)
gs.run()
max_subgraphs = gs._max_subgraphs
results = self.get_multiple_results(gs,max_subgraphs)
solution_1 = ('2','v 0 A v 1 AA v 2 B v 3 C v 4 D v 5 E v 6 F v 7 G e 0 1 m e 1 2 n e 1 5 q e 2 3 o e 3 4 p e 5 6 r e 6 7 s ','8')
solution_2 = ('3','v 0 A v 1 AA v 2 B v 3 E e 0 1 m e 1 2 n e 1 3 q ','4')
solutions = [solution_1, solution_2]
self.updateOutput(results)
self.assertEqual(sorted(solutions), sorted(results))
def main():
if not os.path.exists(FLAGS.database_file_name):
print('{} does not exist.'.format(FLAGS.database_file_name))
sys.exit()
gs = gSpan(database_file_name=FLAGS.database_file_name,
min_support=FLAGS.s,
min_num_vertices=FLAGS.l,
max_num_vertices=FLAGS.u,
max_ngraphs=FLAGS.n,
is_undirected=(FLAGS.d == 0),
verbose=(FLAGS.v != 0),
visualize=(FLAGS.p != 0),
where=(FLAGS.w != 0))
gs.run()
gs.time_stats()
def test_testcase_02(self):
gs = gSpan(
database_file_name="../graphdata/graph.data.testcase.2",
min_support=2
)
gs.run()
max_subgraphs = gs._max_subgraphs
results = self.get_single_result(gs, max_subgraphs)
solution_support = "2"
solution_description = "v 0 A v 1 B v 2 C e 0 1 x e 0 2 z e 1 2 y "
solution_num_vert = "3"
solution_1 = (solution_support, solution_description, solution_num_vert)
solutions = [solution_1]
self.updateOutput(results)
self.assertEqual(sorted(solutions), sorted(results))
def find_subgraph(group_id, is_generalise=0, has_root=1):
graphs,min_support=read_gml_graphs('../with_tags',
group_id=group_id,
is_generalise=is_generalise,
has_root=has_root)
gs = gSpan(
database_file_name='../gSpan/graphdata/graph.data.5',
min_support=min_support,
min_num_vertices=2,
max_num_vertices=float('inf'),
max_ngraphs=float('inf'),
is_undirected=0,
verbose=0,
visualize=0,
where=0)
gs.graphs=graphs
logging.info('Number of graphs = %s, min_support = %s, min_num_vertices = %s',len(gs.graphs), gs.min_support, gs.min_num_vertices)
gs.run()
gs.report_df.to_csv('gen/group'+str(group_id)+'_hubermas'+str(is_generalise)+'_root'+str(has_root)+'_supp'+str(gs.min_support)+'_min'+str(gs.min_num_vertices)+'.csv', sep=';', encoding='cp1251')
def main(FLAGS):
"""Run gSpan."""
if not os.path.exists(FLAGS.database_file_name):
print('{} does not exist.'.format(FLAGS.database_file_name))
sys.exit()
gs = gSpan(
database_file_name=FLAGS.database_file_name,
min_support=FLAGS.min_support,
min_num_vertices=FLAGS.lower_bound_of_num_vertices,
max_num_vertices=FLAGS.upper_bound_of_num_vertices,
max_ngraphs=FLAGS.num_graphs,
is_undirected=(not FLAGS.directed),
verbose=FLAGS.verbose,
visualize=FLAGS.plot,
where=FLAGS.where
)
gs.run()
gs.time_stats()
return gs
def test_testcase_10(self):
gs = gSpan(
database_file_name="../graphdata/graph.data.testcase.10",
min_support=2
)
gs.run()
max_subgraphs = gs._max_subgraphs
results = self.get_multiple_results(gs,max_subgraphs)
solution_support_1 = "3"
solution_description_1 = 'v 0 A v 1 D v 2 B v 3 C e 0 1 y e 0 2 z e 2 3 x '
solution_num_vert_1 = "4"
solution_1 = (solution_support_1, solution_description_1, solution_num_vert_1)
solution_support_2 = "2"
solution_description_2 = 'v 0 A v 1 D v 2 E v 3 B v 4 C e 0 1 y e 0 3 z e 1 2 w e 3 4 x '
solution_num_vert_2 = "5"
solution_2 = (solution_support_2, solution_description_2, solution_num_vert_2)
solutions = [solution_1, solution_2]
self.updateOutput(results)
self.assertEqual(sorted(solutions), sorted(results))
def main(FLAGS=None):
"""Run gSpan."""
if FLAGS is None:
FLAGS, _ = parser.parse_known_args(args=sys.argv[1:])
if not os.path.exists(FLAGS.database_file_name):
print('{} does not exist.'.format(FLAGS.database_file_name))
sys.exit()
gs = gSpan(database_file_name=FLAGS.database_file_name,
min_support=FLAGS.min_support,
min_num_vertices=FLAGS.lower_bound_of_num_vertices,
max_num_vertices=FLAGS.upper_bound_of_num_vertices,
max_ngraphs=FLAGS.num_graphs,
is_undirected=(not FLAGS.directed),
verbose=FLAGS.verbose,
visualize=FLAGS.plot,
where=FLAGS.where)
test = gs.run()
gs.time_stats()
return gs
def test_testcase_08(self):
gs = gSpan(
database_file_name="../graphdata/graph.data.testcase.8",
min_support=2
)
gs.run()
max_subgraphs = gs._max_subgraphs
results = self.get_multiple_results(gs,max_subgraphs)
solution_support_1 = "3"
solution_description_1 = 'v 0 A v 1 B v 2 C v 3 D e 0 1 w e 0 2 x e 0 3 y '
solution_num_vert_1 = "4"
solution_1 = (solution_support_1, solution_description_1, solution_num_vert_1)
solution_support_2 = "2"
solution_description_2 = 'v 0 A v 1 B v 2 C v 3 D v 4 E e 0 1 w e 0 2 x e 0 3 y e 0 4 z '
solution_num_vert_2 = "5"
solution_2 = (solution_support_2, solution_description_2, solution_num_vert_2)
solutions = [solution_1, solution_2]
self.updateOutput(results)
self.assertEqual(sorted(solutions), sorted(results))
